Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

644
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
644

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Image quality improvement in single plane-wave imaging using deep learning.

Ultrasonics·2024
Same author

Pose Estimation of Ultrasound Probe Using CNN and RNN with Image Reconstruction Loss.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2023
Same author

Face Attribute Estimation Using Multi-Task Convolutional Neural Network.

Journal of imaging·2022
See all related articles

Related Experiment Video

Updated: Jun 29, 2025

Determining 3D Flow Fields via Multi-camera Light Field Imaging
14:25

Determining 3D Flow Fields via Multi-camera Light Field Imaging

Published on: March 6, 2013

16.6K

Neural Radiance Field-Inspired Depth Map Refinement for Accurate Multi-View Stereo.

Shintaro Ito1, Kanta Miura1, Koichi Ito1

  • 1Graduate School of Information Sciences, Tohoku University, 6-6-05, Aramaki Aza Aoba, Sendai 9808579, Japan.

Journal of Imaging
|March 27, 2024
PubMed
Summary

This study refines depth map estimation by combining Multi-View Stereo (MVS) and Neural Radiance Fields (NeRF). The novel approach enhances accuracy at object surfaces and boundaries for better 3D scene reconstruction.

Keywords:
3D reconstructiondepth map estimationmulti-view stereoneural radiance fields

More Related Videos

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
05:12

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

2.0K
Stereo-Imaging System DLT Calibration to Capture 3D In Situ Displacements of Stretched Peripheral Nerves
06:26

Stereo-Imaging System DLT Calibration to Capture 3D In Situ Displacements of Stretched Peripheral Nerves

Published on: January 12, 2024

390

Related Experiment Videos

Last Updated: Jun 29, 2025

Determining 3D Flow Fields via Multi-camera Light Field Imaging
14:25

Determining 3D Flow Fields via Multi-camera Light Field Imaging

Published on: March 6, 2013

16.6K
Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
05:12

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

2.0K
Stereo-Imaging System DLT Calibration to Capture 3D In Situ Displacements of Stretched Peripheral Nerves
06:26

Stereo-Imaging System DLT Calibration to Capture 3D In Situ Displacements of Stretched Peripheral Nerves

Published on: January 12, 2024

390

Area of Science:

  • Computer Vision
  • 3D Reconstruction
  • Machine Learning

Background:

  • Multi-View Stereo (MVS) excels at depth estimation on object surfaces.
  • Neural Radiance Fields (NeRF) are effective for depth estimation at object boundaries.
  • Integrating MVS and NeRF offers potential for improved depth map accuracy.

Purpose of the Study:

  • To propose a novel method for refining depth maps using iterative Neural Radiance Field (NeRF) optimization.
  • To leverage the complementary strengths of MVS and NeRF for enhanced depth map estimation.
  • To improve the accuracy of depth map refinement through the introduction of a Huber loss function.

Main Methods:

  • Iterative optimization of Neural Radiance Fields (NeRF) to refine depth maps.
  • Integration of Multi-View Stereo (MVS) depth estimations with NeRF.
  • Application of a Huber loss function during NeRF optimization to constrain errors.

Main Results:

  • The proposed method demonstrates superior performance in depth map refinement compared to conventional techniques.
  • Experiments on the Redwood-3dscan and DTU datasets validate the effectiveness of the approach.
  • The combination of MVS and NeRF, with Huber loss, yields more accurate depth maps.

Conclusions:

  • The proposed method effectively refines depth maps by synergistically combining MVS and NeRF.
  • The Huber loss contributes to improved accuracy in NeRF-based depth map refinement.
  • This approach offers a significant advancement in 3D scene reconstruction accuracy.